Information processing apparatus and information processing method

Abstract

There is provided an information processing apparatus that can perform learning of a neural network more efficiently, the information processing apparatus including: an acquisition section configured to acquire a semantic network, identification information of data, and a label; and a learning section configured to learn a classification model that classifies the data into the label, on a basis of the semantic network, the identification information, and the label that have been acquired by the acquisition section.

1 . An information processing apparatus comprising:
 an acquisition section configured to acquire a semantic network including information indicating a relationship between nodes, identification information of data, and a label corresponding to the node forming the semantic network; and   a learning section configured to learn a classification model that classifies the data into the label, on a basis of the semantic network, the identification information, and the label that have been acquired by the acquisition section, using a learning criterion as to whether a plurality of the labels included in a classification result of the data conforms to the relationship between the nodes in the semantic network.   
     
     
         2 . (canceled) 
     
     
         3 . (canceled) 
     
     
         4 . (canceled) 
     
     
         5 . The information processing apparatus according to  claim 1 , wherein the learning section performs learning on a basis of a feedback to output information regarding a learning result. 
     
     
         6 . The information processing apparatus according to  claim 5 , wherein the output information includes information that proposes an input of the semantic network that is new. 
     
     
         7 . The information processing apparatus according to  claim 6 , wherein the output information includes information that proposes the semantic network that is new. 
     
     
         8 . The information processing apparatus according to  claim 7 , wherein the output information includes information indicating the semantic network inferred from another label associated with other data. 
     
     
         9 . The information processing apparatus according to  claim 5 , wherein the output information includes information that proposes association of the label that is new, with the data. 
     
     
         10 . The information processing apparatus according to  claim 5 , wherein
 the classification model is mounted by a neural network, and   the output information includes output values of one or more units included in the neural network.   
     
     
         11 . The information processing apparatus according to  claim 10 , wherein the output information includes a clustering result of the output values. 
     
     
         12 . The information processing apparatus according to  claim 10 , wherein the one or more units correspond to a plurality of units constituting an intermediate layer. 
     
     
         13 . The information processing apparatus according to  claim 10 , wherein the one or more units correspond to one unit of an intermediate layer. 
     
     
         14 . The information processing apparatus according to  claim 5 , wherein the output information includes a co-occurrence histogram of the label. 
     
     
         15 . An information processing method executed by a processor, the information processing method comprising:
 acquiring a semantic network including information indicating a relationship between nodes, identification information of data, and a label corresponding to the node forming the semantic network; and   learning a classification model that classifies the data into the label, on a basis of the semantic network, the identification information, and the label that have been acquired, using a learning criterion as to whether a plurality of the labels included in a classification result of the data conforms to the relationship between the nodes in the semantic network.